Prediction of movies box office performance using social media

This study applies data mining tools to generate interesting patterns for predicting box office performance of movies using data collected from multiple social media and web sources including Twitter, YouTube and the IMDb movie database.

Abstract

In this study, we apply data mining tools to generate interesting patterns for predicting box office performance of movies using data collected from multiple social media and web sources including Twitter, YouTube and the IMDb movie database. The prediction is based on decision factors derived from a historical movie database, followers count from Twitter, and sentiment analysis of YouTube viewers' comments. We label the prediction in three classes, Hit, Neutral and Flop, using Weka's K-Means clustering tool. Interesting patterns for prediction are generated by Weka's J48. Since our prediction is for movies yet to be released in summer 2013, the performance of the final results will be validated by a follow-up study.